medical-research-toolkit
Warn
Audited by Snyk on Mar 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's required workflows and examples (SKILL.md and scripts/drug-repurposing-workflow.md) instruct the agent to call the public MCP endpoint (https://mcp.cloud.curiloo.com/tools/unified/mcp) to fetch and synthesize content from open third‑party sources (PubMed, ClinicalTrials.gov, OpenFDA, ChEMBL, OMIM, preprints, etc.), meaning untrusted public content is ingested and used to drive decisions and recommendations.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata